Clearminutes
AI meeting notes that never leave your machine. 100% local.
Clearminutes launched on May 26, 2026 with 3 votes, #3,449 of 20,538 launches that month and more than 50% of that year's launches.
What it does
Privacy-first AI meeting assistant that transcribes, summarises, and extracts action items - entirely on your device. No meeting bot. No cloud by default. Runs Whisper.cpp locally with GPU acceleration. Free tier with unlimited transcription.
Local-first AI meeting transcription and summaries. Your audio never leaves your machine. No cloud required. Action items, auto-summaries, and TickTick sync.
Clearminutes is the AI meeting assistant that records your call, transcribes every word in real time with on-device Whisper, labels who said what, and writes a clean summary with action items the second you stop. Audio never leaves your machine. No cloud, no bot, no upload. Telemetry is off by default: opt in during onboarding only if you want to help. Even then it's anonymous usage stats, never your audio or transcript. Clearminutes is the local-first AI meeting assistant for people who can't send their calls to someone else's server. Every other tool uploads your audio. Clearminutes runs Whisper transcription and AI summaries locally on your Mac, Windows, or Linux machine. Zero outbound…from clearminutes.app
Does a similar job
all alternatives →




Note67 - Private Meeting Notes AssistantDec 2025 · note67.com · ▲10Open source, local-first AI meeting assistant
More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video

Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com